School of Medicine and Surgery, University of Milan-Bicocca, Monza, Lombardy, Italy.
Centro di Ricerca Interdipartimentale Bicocca Bioinformatics Biostatistics and Bioimaging Centre - B4, Università Degli Studi Di Milano-Bicocca, Milan, Italy.
Eur J Nucl Med Mol Imaging. 2022 Aug;49(10):3401-3411. doi: 10.1007/s00259-022-05783-z. Epub 2022 Apr 11.
The present pilot study investigates the putative role of radiomics from [18F]FDG PET/CT scans to predict PD-L1 expression status in non-small cell lung cancer (NSCLC) patients.
In a retrospective cohort of 265 patients with biopsy-proven NSCLC, 86 with available PD-L1 immunohistochemical (IHC) assessment and [18F]FDG PET/CT scans have been selected to find putative metabolic markers that predict PD-L1 status (< 1%, 1-49%, and ≥ 50% as per tumor proportion score, clone 22C3). Metabolic parameters have been extracted from three different PET/CT scanners (Discovery 600, Discovery IQ, and Discovery MI) and radiomics features were computed with IBSI compliant algorithms on the original image and on images filtered with LLL and HHH coif1 wavelet, obtaining 527 features per tumor. Univariate and multivariate analysis have been performed to compare PD-L1 expression status and selected radiomic features.
Of the 86 analyzed cases, 46 (53%) were negative for PD-L1 IHC, 13 (15%) showed low PD-L1 expression (1-49%), and 27 (31%) were strong expressors (≥ 50%). Maximum standardized uptake value (SUVmax) demonstrated a significant ability to discriminate strong expressor cases at univariate analysis (p = 0.032), but failed to discriminate PD-L1 positive patients (PD-L1 ≥ 1%). Three radiomics features appeared the ablest to discriminate strong expressors: (1) a feature representing the average high frequency lesion content in a spherical VOI (p = 0.009); (2) a feature assessing the correlation between adjacent voxels on the high frequency lesion content (p = 0.004); (3) a feature that emphasizes the presence of small zones with similar grey levels inside the lesion (p = 0.003). The tri-variate linear discriminant model combining the three features achieved a sensitivity of 81% and a specificity of 82% in the test. The ability of radiomics to predict PD-L1 positive patients was instead scarce.
Our data indicate a possible role of the [18F]FDG PET radiomics in predicting strong PD-L1 expression; these preliminary data need to be confirmed on larger or single-scanner series.
本初步研究旨在探讨[18F]FDG PET/CT 扫描的放射组学在非小细胞肺癌（NSCLC）患者中预测 PD-L1 表达状态的潜在作用。
在 265 例经活检证实的 NSCLC 患者的回顾性队列中，选择了 86 例有可用 PD-L1 免疫组织化学（IHC）评估和[18F]FDG PET/CT 扫描的患者，以寻找潜在的代谢标志物来预测 PD-L1 状态（根据肿瘤比例评分，克隆 22C3，<1%、1-49%和≥50%）。从三种不同的 PET/CT 扫描仪（Discovery 600、Discovery IQ 和 Discovery MI）中提取代谢参数，并使用 IBSI 兼容算法在原始图像和经过 LLL 和 HHH coif1 小波滤波的图像上计算放射组学特征，每个肿瘤获得 527 个特征。对 PD-L1 表达状态和选定的放射组学特征进行单因素和多因素分析。
在分析的 86 例病例中，46 例（53%）PD-L1 IHC 阴性，13 例（15%）低表达（1-49%），27 例（31%）强表达（≥50%）。单因素分析显示，最大标准化摄取值（SUVmax）在区分强表达病例方面具有显著能力（p=0.032），但无法区分 PD-L1 阳性患者（PD-L1≥1%）。三个放射组学特征能够最有效地区分强表达者：（1）代表球形 VOI 中高频病变含量平均值的特征（p=0.009）；（2）评估高频病变含量上相邻体素之间相关性的特征（p=0.004）；（3）强调病变内具有相似灰度级的小区域存在的特征（p=0.003）。结合这三个特征的三变量线性判别模型在测试中达到了 81%的敏感性和 82%的特异性。放射组学预测 PD-L1 阳性患者的能力则较差。
我们的数据表明[18F]FDG PET 放射组学在预测强 PD-L1 表达方面可能具有一定作用；这些初步数据需要在更大或单扫描仪系列中进行验证。
